mlsanityData to 14 Oct 2026

Point4D: Long-range 4D Motion Reconstruction

arXiv 2609.09145 ↗First posted 8 Sep 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce Point4D, a feed-forward model for 4D reconstruction of long-range video sequences. Point4D is able to reliably infer dense per-point 3D trajectories across multi-hundred-frame videos, unlike existing 4D methods that are limited to short input windows of at most a few dozen frames. A key innovation that enables this is our flexible 3D query-based motion decoder that decouples trajectory prediction from image-plane visibility. The predicted 3D endpoints are then directly re-queried in the next chunk without re-projection or matching. Furthermore, we show that extracting and reusing a visual descriptor from an arbitrary frame where the point is visible leads to better performance than relying solely on the source patch. Overall, Point4D achieves state-of-the-art performance across diverse long-video tracking benchmarks spanning over 200 frames and largely outperforms previous feed-forward 4D method. Project page: https://point-4d.github.io

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 50 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

45 of 50 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2021Vision Transformers for Dense Predictioncited by 1,803
  5. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  6. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  7. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  8. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  9. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  10. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  11. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  12. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
33 more
  1. 2022Kubric: A scalable dataset generatorcited by 381
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  3. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 287
  4. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  5. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 263
  6. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  7. 2023Tracking Everything Everywhere All at Oncecited by 193
  8. 2019ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residualscited by 181
  9. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 181
  10. 2025Streaming 4D Visual Geometry Transformercited by 161
  11. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  12. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 129
  13. 2024CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videoscited by 128
  14. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 115
  15. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  16. 2025St4RTrack: Simultaneous 4D Reconstruction and Tracking in the Worldcited by 89
  17. 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3Dcited by 72
  18. 2025TAPIP3D: Tracking Any Point in Persistent 3D Geometrycited by 69
  19. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 65
  20. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 62
  21. 2026InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streamscited by 56
  22. 2025Efficiently Reconstructing Dynamic Scenes One D4RT at a Timecited by 54
  23. 2026LoGeR: Long-Context Geometric Reconstruction with Hybrid Memorycited by 39
  24. 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 35
  25. 2026V-DPM: 4D Video Reconstruction with Dynamic Point Mapscited by 34
  26. 2025Trace Anything: Representing Any Video in 4D via Trajectory Fieldscited by 33
  27. 2024SceneTracker: Long-term Scene Flow Estimation Networkcited by 26
  28. 2026ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Trainingcited by 26
  29. 2023DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videoscited by 25
  30. 2025BEDLAM2.0: Synthetic Humans and Cameras in Motioncited by 25
  31. 20264RC: 4D Reconstruction via Conditional Querying Anytime and Anywherecited by 22
  32. 2026Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learningcited by 9
  33. 2026Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flowcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wildcited by 0